Foundations of Non-Bayesian Social Learning

In this paper, we study the problem of non-Bayesian learning over social networks by taking an axiomatic approach. As our main behavioral assumption, we postulate that agents follow social learning rules that satisfy imperfect recall, according to which they treat the current beliefs of their neighbors as sufficient statistics for all the information available to them. We establish that as long as imperfect recall represents the only point of departure from Bayesian rationality, agents’ social learning rules take a log-linear form. Our approach also enables us to provide a taxonomy of behavioral assumptions that underpin various non-Bayesian models of learning, including the canonical model of DeGroot. We then show that for a fairly large class of learning rules, the form of bounded rationality represented by imperfect recall is not an impediment to asymptotic learning, as long as agents assign weights of equal orders of magnitude to every independent piece of information. Finally, we show how the dispersion of information among different individuals in the social network determines the rate of learning.

[1]  D. Blackwell.  Equivalent Comparisons of Experiments , 1953 .

[2]  M. Degroot.  Reaching a Consensus , 1974 .

[3]  A. Mucci,et al.  Another martingale convergence theorem , 1976 .

[4]  E. Seneta,et al.  Towards consensus: some convergence theorems on repeated averaging , 1977, Journal of Applied Probability.

[5]  C. Wagner,et al.  Rational Consensus in Science and Society: A Philosophical and Mathematical Study , 1981 .

[6]  C. Wagner,et al.  Rational Consensus in Science and Society , 1981 .

[7]  William McCuaig,et al.  A simple proof of Menger's theorem , 1984, J. Graph Theory.

[8]  Charles R. Johnson,et al.  Matrix analysis , 1985, Statistical Inference for Engineers and Data Scientists.

[9]  J. P. Lasalle.  The stability and control of discrete processes , 1986 .

[10]  D. Isenberg.  Group polarization: A critical review and meta-analysis. , 1986 .

[11]  E. Lehmann.  Comparing Location Experiments , 1988 .

[12]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[13]  A. Banerjee,et al.  A Simple Model of Herd Behavior , 1992 .

[14]  S. Bikhchandani,et al.  You have printed the following article : A Theory of Fads , Fashion , Custom , and Cultural Change as Informational Cascades , 2007 .

[15]  Robert J. Plemmons,et al.  Nonnegative Matrices in the Mathematical Sciences , 1979, Classics in Applied Mathematics.

[16]  J. Steele.  Le Cam's inequality and poisson approximations , 1994 .

[17]  Lones Smith,et al.  Pathological Outcomes of Observational Learning , 2000 .

[18]  Joel L. Schrag,et al.  First Impressions Matter: A Model of Confirmatory Bias , 1999 .

[19]  S. Goyal,et al.  Learning from neighbours , 1998 .

[20]  Cass R. Sunstein,et al.  Deliberative Trouble - Why Groups Go to Extremes , 2000 .

[21]  P. DeMarzo,et al.  Persuasion Bias, Social Influence, and Uni-Dimensional Opinions , 2001 .

[22]  J. Steele.  The Cauchy–Schwarz Master Class: References , 2004 .

[23]  Matthew O. Jackson,et al.  Näıve Learning in Social Networks : Convergence , Influence , and the Wisdom of Crowds ∗ , 2007 .

[24]  E. Seneta.  Non-negative Matrices and Markov Chains , 2008 .

[25]  Ilan Lobel,et al.  BAYESIAN LEARNING IN SOCIAL NETWORKS , 2008 .

[26]  Asuman E. Ozdaglar,et al.  Spread of (Mis)Information in Social Networks , 2009, Games Econ. Behav..

[27]  M. Rabin,et al.  Naïve Herding in Rich-Information Settings , 2010 .

[28]  Manuel Mueller-Frank,et al.  A general framework for rational learning in social networks , 2011 .

[29]  Veronika Grimm,et al.  An experiment on learning in a multiple games environment , 2012, J. Econ. Theory.

[30]  Ali Jadbabaie,et al.  Non-Bayesian Social Learning , 2011, Games Econ. Behav..

[31]  B. Golub,et al.  How Homophily Affects the Speed of Learning and Best Response Dynamics , 2012 .

[32]  Arun G. Chandrasekhar,et al.  Network Structure and the Aggregation of Information: Theory and Evidence from Indonesia , 2012 .

[33]  Elchanan Mossel,et al.  Strategic Learning and the Topology of Social Networks , 2012, ArXiv.

[34]  Pooya Molavi,et al.  Information Heterogeneity and the Speed of Learning in Social Networks , 2013 .

[35]  Arun G. Chandrasekhar,et al.  The Diffusion of Microfinance , 2012, Science.

[36]  M. Rabin,et al.  Extensive Imitation is Irrational and Harmful , 2014 .

[37]  Mallesh M. Pai,et al.  Social Learning with Costly Search , 2014 .

[38]  I. Lobel,et al.  Information Diffusion in Networks through Social Learning , 2014 .

[39]  Lin Wang,et al.  Social learning with time-varying weights , 2014, Journal of Systems Science and Complexity.

[40]  Pooya Molavi,et al.  (Non-)Bayesian learning without recall , 2014, 53rd IEEE Conference on Decision and Control.

[41]  Elchanan Mossel,et al.  WHEN MORE INFORMATION REDUCES THE SPEED OF LEARNING , 2015 .

[42]  Manuel Mueller-Frank,et al.  A General Model of Boundedly Rational Observational Learning: Theory and Evidence , 2015 .

[43]  Arun G. Chandrasekhar,et al.  Testing Models of Social Learning on Networks: Evidence from a Lab Experiment in the Field , 2015 .

[44]  Syngjoo Choi,et al.  Networks in the laboratory , 2015 .

[45]  Tristan Gagnon-Bartsch,et al.  Naive Social Learning, Mislearning, and Unlearning , 2016 .

[46]  Ilan Lobel,et al.  Preferences, Homophily, and Social Learning , 2014, Oper. Res..

[47]  Emily Breza,et al.  Field Experiments, Social Networks, and Development , 2016 .

[48]  Evan Sadler,et al.  Learning in Social Networks , 2016 .

[49]  Katja Gruenewald,et al.  Theory Of Games And Statistical Decisions , 2016 .

[50]  Michael S. Johannes,et al.  Asset Pricing When 'This Time is Different' , 2016 .

[51]  Bailey,et al.  Asset Pricing , 2017, Encyclopedia of GIS.

[52]  V. Grimm,et al.  Experiments on Belief Formation in Networks , 2018, Journal of the European Economic Association.